NEURAL NETWORK METHOD OF ESTIMATING CONSTRUCTION TECHNOLOGY ACCEPTABILITY

The authors present a neural network (NN) based approach for predicting the potential acceptability of a new construction technology. The acceptability of a technology for a target operation is defined as the proportion of users that select that technology as compared to a conventional (base) technology. All existing alternative technologies for the target operation are collected as samples for study. The performance characteristics of each sample technology are stored in a vector comprising eigenvalues obtained by using the analytical hierarchy process method, and its acceptability is determined using a poll. The obtained performance-acceptability pairs are used to train a neural network using the back-propagation algorithm. The trained network can then predict the acceptability of a new technology, based on its performance attributes. Possible applications of the approach as well as information sources for training set construction are discussed. A new concrete distribution system for concrete placement on a mid-rise building project is used as an example to estimate adoption of the new technology. Results are promising for the NN approach with simulated data, especially when the poll size used is sufficiently large.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/8675438
• Corporate Authors:

  American Society of Civil Engineers

  345 East 47th Street
  New York, NY  United States  10017-2398
• Authors:
  • Chao, L-C
  • Skibniewski, M J
• Publication Date: 1995-3

Language

• English

Media Info

• Features: Appendices; Figures; References; Tables;
• Pagination: p. 130-142
• Serial:
  • Journal of Construction Engineering and Management
  • Volume: 121
  • Issue Number: 1
  • Publisher: American Society of Civil Engineers
  • ISSN: 0733-9364
  • EISSN: 1943-7862
  • Serial URL: http://ascelibrary.org/journal/jcemd4

Subject/Index Terms

• TRT Terms: Acceptance; Algorithms; Construction management; Estimating; Estimation theory; Mathematical prediction; Neural networks; Performance; Technology
• Uncontrolled Terms: Acceptability; Performance characteristics
• Old TRIS Terms: Construction operations
• Subject Areas: Construction; Data and Information Technology; Highways; Planning and Forecasting; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 00680651
• Record Type: Publication
• Files: TRIS
• Created Date: Jun 27 1995 12:00AM